NLPSandbox.io is an open platform for benchmarking modular natural language processing (NLP) tools on both public and private datasets. Academics, students, and industry professionals are invited to browse the available tasks and participate by developing and submitting an NLP Sandbox tool.
This repository packages NeuroNER as an NLP Sandbox PHI annotator. The performance of this tool can be viewed and compared to the performance of other PHI annotators on NLPSandbox.io.
Annotations supported by NeuroNER:
| Annotation | Schema | Supported |
|---|---|---|
| Contact | TextContactAnnotation | Yes |
| Date | TextDateAnnotation | Yes |
| ID | TextIdAnnotation | Yes |
| Location | TextLocationAnnotation | Yes |
| Person Name | TextPersonNameAnnotation | No |
- Specification
- Requirements
- Usage
- Development
- Versioning
- Benchmarking on NLPSandbox.io
- Citation
- Contributing
- License
- NLP Sandbox tool version: 1.1.1
- NLP Sandbox schemas version: 1.2.0
- Docker image: docker.synapse.org/syn22277123/phi-annotator-neuroner
- Docker Engine >=19.03.0
The command below starts this NLP Sandbox PHI annotator locally.
docker compose up --buildYou can stop the container run with Ctrl+C, followed by docker compose down.
Create a Conda environment.
conda create --name phi-annotator-neuroner python=3.7 -y
conda activate phi-annotator-neuronerNote: NeuroNER only support up to Python 3.7.
Download the word embeddings file (too large to be tracked on GitHub).
curl -O http://neuroner.com/data/word_vectors/glove.6B.100d.zip
unzip glove.6B.100d.zip -d server/data/word_vectors/
Install and start this NLP Sandbox tool.
cd server && pip install -r requirements.txt
python -m openapi_serverThis NLP Sandbox tool provides a web interface that you can use to annotate clinical notes. This web client has been automatically generated by openapi-generator. To access the UI, open a new tab in your browser and navigate to one of the following address depending on whether you are running the tool using Docker (production) or Python (development).
- Using Docker: http://localhost/ui
- Using Python: http://localhost:8080/ui
Please refer to the section Development of the NLP Sandbox PHI Annotator
example for information on how to develop an NLP Sandbox PHI annotator in
Python-Flask and other programming languages-frameworks.
This repository uses semantic versioning to track the releases of this tool. This repository uses "non-moving" GitHub tags, that is, a tag will always point to the same git commit once it has been created.
The artifact published by the CI/CD workflow of this GitHub repository is a Docker image pushed to the Synapse Docker Registry. This table lists the image tags pushed to the registry.
| Tag name | Moving | Description |
|---|---|---|
latest |
Yes | Latest stable release. |
edge |
Yes | Latest commit made to the default branch. |
edge-<sha> |
No | Same as above with the reference to the git commit. |
<major>.<minor>.<patch> |
No | Stable release. |
You should avoid using a moving tag like latest when deploying containers in
production, because this makes it hard to track which version of the image is
running and hard to roll back.
Visit nlpsandbox.io for instructions on how to submit your NLP Sandbox tool and evaluate its performance.
- If you use NeuroNER in your publications, please follow the citation guidelines given by the authors of NeuroNER.
- If you use this NLP Sandbox tool or resources from NLPSandbox.io, please follow these citation guidelines.
Thinking about contributing to this project? Get started by reading our contribution guide.